{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:27Y2EADLLCZN3YOKHXM5H4N3RU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"095d2d6cddbb1149ad8feb8149dfab0b321c465c4887e69694a65a1ef2b17235","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T14:18:16Z","title_canon_sha256":"0604f175f888c6c94c330dd5f8eb3db32aa3d1267a8b9ad981afae0b18d71d01"},"schema_version":"1.0","source":{"id":"2505.13157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13157","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13157v1","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13157","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"27Y2EADLLCZN","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"27Y2EADLLCZN3YOK","created_at":"2026-07-05T11:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"27Y2EADL","created_at":"2026-07-05T11:05:25Z"}],"graph_snapshots":[{"event_id":"sha256:eaac7179cb89a264c2f03c8de168575b3e91ccc7ffa4b3b5194509216e22b5c4","target":"graph","created_at":"2026-07-05T11:05:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.13157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) demonstrate a notable capacity for adopting personas and engaging in role-playing. However, evaluating this ability presents significant challenges, as human assessments are resource-intensive and automated evaluations can be biased. To address this, we introduce Role-Playing Eval (RPEval), a novel benchmark designed to assess LLM role-playing capabilities across four key dimensions: emotional understanding, decision-making, moral alignment, and in-character consistency. This article details the construction of RPEval and presents baseline evaluations. Our code and","authors_text":"Julian Alvarez, Walter Nuninger, Yassine El Boudouri, Yvan Peter","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T14:18:16Z","title":"Role-Playing Evaluation for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13157","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ce25d1a0c08166d1c09b71b0de3dc6498b4b77ee50721d4a1442f8ca16b8a0f0","target":"record","created_at":"2026-07-05T11:05:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"095d2d6cddbb1149ad8feb8149dfab0b321c465c4887e69694a65a1ef2b17235","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T14:18:16Z","title_canon_sha256":"0604f175f888c6c94c330dd5f8eb3db32aa3d1267a8b9ad981afae0b18d71d01"},"schema_version":"1.0","source":{"id":"2505.13157","kind":"arxiv","version":1}},"canonical_sha256":"d7f1a2006b58b2dde1ca3dd9d3f1bb8d2f68449918d044e786eecbd1473a1ecd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7f1a2006b58b2dde1ca3dd9d3f1bb8d2f68449918d044e786eecbd1473a1ecd","first_computed_at":"2026-07-05T11:05:25.988035Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:25.988035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"65QTkATdIY4jxetrDaoGWDIzBOnhSAslrV8GOw9DoPbHb4ycDpPH14+j28i4/v3Y2UNuJ3ay5os0d4piUTLrDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:25.988519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce25d1a0c08166d1c09b71b0de3dc6498b4b77ee50721d4a1442f8ca16b8a0f0","sha256:eaac7179cb89a264c2f03c8de168575b3e91ccc7ffa4b3b5194509216e22b5c4"],"state_sha256":"7d3c1711072481c3547f82f583a7b6185750166cd712d81b434adefd9c9a0c92"}